Open dtch1997 opened 4 days ago
Some quick sanity checks.
The gold standard would be to compare to Michael Hanna's implementation and ensure that we get the same scores per edge.
It's probably faster to first implement the pruning and evaluation code (which we'll need eventually anyway) and check if our circuit metrics match his.
In
'notebooks/test_our_attrib_matches_original.ipynb
, we check our attribution scores against those computed by the original implementation.Annoyingly, the scores don't match. Have to figure out why this is the case...